Hate speech is one type of harmful online content which directly attacks or promotes hate
towards a group or an individual member based on their actual or perceived aspects of …

We survey 146 papers analyzing" bias" in NLP systems, finding that their motivations are
often vague, inconsistent, and lacking in normative reasoning, despite the fact that …

Biased associations have been a challenge in the development of classifiers for detecting
toxic language, hindering both fairness and accuracy. As potential solutions, we investigate …

In current hate speech datasets, there exists a high correlation between annotators'
perceptions of toxicity and signals of African American English (AAE). This bias in annotated …

Cyberbullying is a widespread adverse phenomenon among online social interactions in
today's digital society. While numerous computational studies focus on enhancing the …

Automated systems for detecting harmful social media content are afflicted by a variety of
biases, some of which originate in their training datasets. In particular, some systems have …

Robustness is of central importance in machine learning and has given rise to the fields of
domain generalization and invariant learning, which are concerned with improving …

Automated filtering of toxic conversations may help an Open-source software (OSS)
community to maintain healthy interactions among the project participants. Although, several …

Natural language processing (NLP) systems are now ubiquitous. Yet the benefits of these
language technologies do not accrue evenly to all users, and indeed they can be harmful; …

Social media has become an essential facet of modern society and is quickly becoming
indispensable. The ubiquity of social media, while having its benefits, also opens up people …